 Composable Planning with AttributesInternational Conference on Machine Learning (ICML), 2018 |
 Learning by Playing - Solving Sparse Reward Tasks from ScratchInternational Conference on Machine Learning (ICML), 2018 Martin Riedmiller Agrim Gupta Thomas Lampe Michael Neunert Jonas Degrave T. Wiele Volodymyr Mnih N. Heess Jost Tobias Springenberg |
 Temporal Difference Models: Model-Free Deep RL for Model-Based ControlInternational Conference on Learning Representations (ICLR), 2018 |
 RLlib: Abstractions for Distributed Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2017 |
 |
 Intrinsically Motivated Goal Exploration Processes with Automatic
Curriculum LearningJournal of machine learning research (JMLR), 2017 |
 |
